search

HzDmS / gaze_redirection

[Official Implementation] Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks, He et.al. ICCV 2019
MIT License
137 stars 21 forks source link

How to restore checkpoint and only use generator to generate image #8

Open r06631001 opened 4 years ago

r06631001 commented 4 years ago

function eval in model.py I can successfully generate targets, genes and reals by my saved checkpoint model. However, I want to use only generator to generate the eye with target angle. That is, input: x_test_r, angles_test_g, output: 64 x 64 x 3 eye image. So, how to used the restored checkpoint and only use generator to generate image?

Thanks

zhangqianhui commented 4 years ago

You should learn about the tensorflow.

santi-grau commented 2 years ago

function eval in model.py I can successfully generate targets, genes and reals by my saved checkpoint model. However, I want to use only generator to generate the eye with target angle. That is, input: x_test_r, angles_test_g, output: 64 x 64 x 3 eye image. So, how to used the restored checkpoint and only use generator to generate image?

Thanks

Any luck? quite new to all this :( Can run eval on Colab but no idea how to generate w my own images...